Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Multimodal modeling for personalized psychiatry|
|Citation:||Personalised Psychiatry, 2020 / Baune, B. (ed./s), Ch.43, pp.521-536|
|Publisher Place:||London, United Kingdom|
|Scott R. Clark, Micah Cearns, Klaus Oliver Schubert, Bernhard T. Baune|
|Abstract:||Outcomes for people with mental illness are difficult to predict due to the syndromal nature of diagnosis and the complex relationships among clinical and biological predictors and outcomes. Due to the small amounts of variance explained by individual predictors, the application of multivariate modeling techniques is key to improving the accuracy of outcome prediction. The combination of data from multiple modes of clinical and biological assessment shows potential to increase the accuracy of such models. Superior performance may be achieved by combining clinical data with imaging, electrophysiology, and blood-based biomarkers. Multimodal multivariate modeling techniques are central to the development of personalized psychiatry, affording the potential for patient stratification and individual outcome prediction. This chapter outlines the range of multimodal data available, study design, and modeling techniques.|
|Rights:||Copyright © 2020 Elsevier Inc. All rights reserved.|
|Appears in Collections:||Aurora harvest 8|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.